activity
20242026
collaborators

9 papers

cs.LG2026

The Stability of Online Algorithms in Performative Prediction

Gabriele Farina, Juan Carlos Perdomo

The use of algorithmic predictions in decision-making leads to a feedback loop where the models we deploy actively influence the data distributions we see, and later use to retrain…

cs.LG2026

An Efficient Black-Box Reduction from Online Learning to Multicalibration, and a New Route to -Regret Minimization

Gabriele Farina, Juan Carlos Perdomo

We give a Gordon-Greenwald-Marks (GGM) style black-box reduction from online learning to online multicalibration. Concretely, we show that to achieve high-dimensional multicalibrat…

cs.LG2026

Defensive Generation

Gabriele Farina, Juan Carlos Perdomo

We study the problem of efficiently producing, in an online fashion, generative models of scalar, multiclass, and vector-valued outcomes that cannot be falsified on the basis of th…

cs.LG2025

In Defense of Defensive Forecasting

Juan Carlos Perdomo, Benjamin Recht

This tutorial provides a survey of algorithms for Defensive Forecasting, where predictions are derived not by prognostication but by correcting past mistakes. Pioneered by Vovk, De…

cs.CY2025

The Value of Prediction in Identifying the Worst-Off

Unai Fischer-Abaigar, Christoph Kern, Juan Carlos Perdomo

Machine learning is increasingly used in government programs to identify and support the most vulnerable individuals, prioritizing assistance for those at greatest risk over optimi…

cs.CY2025

Revisiting the Predictability of Performative, Social Events

Juan C. Perdomo

Social predictions do not passively describe the future; they actively shape it. They inform actions and change individual expectations in ways that influence the likelihood of the…